Loading...
Loading...
Found 32 Skills
Record a video of an iOS simulator or Android emulator/device screen using argent MCP tools. Use when the user asks to record the screen, capture a video of a flow, interaction, or animation, produce a screen recording, or document app behavior as a video clip.
Synthetic terminal-style screen recording guidance for Remotion `TerminalScene`.
Create annotated animated GIF demos and screen recordings for pull requests and documentation. Covers frame capture, timing, imageio-based GIF creation, and per-frame annotation workflows.
Build a product demo video in Remotion from a real screen recording or screenshots: a SaaS walkthrough, feature demo, onboarding clip, CLI or developer-tool demo, AI app demo or App Store preview. Uses snapcn's Remotion components (@snapcn/screen-recording, cursor-track, laptop-frame, phone-frame, terminal-simulator, prompt-send, answer-stream, status-cycle) so the camera push, clicks, device frames and typed commands come pre-built instead of hand-animated. Triggers: product demo, demo video, remotion demo, product walkthrough, feature demo video, screen recording to video, app demo, SaaS demo, CLI demo, "turn my screen recording into a demo video".
Create, record, edit, replay, or repair reusable Argent e2e test YAML files. Use when the user asks to record, replay, or run an e2e test or a repeatable device path, set up profiling or an A/B comparison, or invoke the authoring engine behind argent-qa-e2e. Also use before repeating three or more interactions. For one-off UI checks, acceptance-driven regression tests, or screen video, use argent-test-ui-flow, argent-qa-e2e, or argent-screen-recording respectively.
Produce a polished local talking-head or narrated screen-recording rough cut without a cloud editor. Use when Codex must clean Chinese or mixed Chinese-English speech, correct product terminology before semantic editing, compress pauses without making speech breathless, preserve source resolution and frame rate, normalize dialogue loudness, generate final-audio subtitle artifacts, or benchmark local output against ChatCut/video-use/chengfeng/AI剪口播.
Turn an approved core topic or script into a video plan that is ready for filming, screen recording, or handoff to a video-production tool. It also supports digital-human videos after the user confirms likeness and voice rights and manually uploads the assets on the platform, as well as animated explainer videos without a real presenter using synthesized voiceovers and AI-generated visuals (educational content, history, and brand stories). It is used to produce voiceover scripts, first-three-second hooks, storyboards, subtitles, screen-recording checklists, covers, hashtags, background music and licensing, digital-human or animation production packages, landscape and vertical versions for multiple platforms, and publishing copy for WeChat Channels, Douyin, Xiaohongshu videos, YouTube landscape videos, and Shorts.
Create high-fidelity web demo animations with "one HTML per shot" for videos/courses/commentary scripts (storyboard demo pages, video-matched demo animations, screen-recording animation webpages, visual shots for science popularization/tech/product launches). Use this Skill whenever users mention: making demo animation webpages for videos, storyboard HTML, shot pages, turning scripts/outlines into animations, webpage versions of video frame designs, recording web animations, or requesting to revamp a batch of existing demo pages. The core lies in a unified cinematic player mechanism + completely distinct visual styles per page + shot language + synchronized sound effects + character expression gags, with fully open and unrestricted content.
Builds standard operating procedures from a guided interview, screen-recording transcript, or existing draft. Use when the user says "write an SOP", "document this process", "make an SOP for X", "I keep redoing this", "delegate this to my VA", "onboarding doc for new hire", "write up how I do this", or asks to audit / clean up an existing SOP. Treats the user as the expert being interviewed and acts as a COO who pushes back on weak steps before they get written down.
Reverse-engineer how a video was made—classify each shot as live action / AI-generated / 3D rendering / 2D animation / stop-motion animation / code-template rendering / screen-recording screenshot / static-image push-in / push-out / still frame, and determine whether live-action footage was AI-processed (face swap, lip sync, stylization). Identify post-production overlays (sentence-by-sentence subtitle timelines, decorative text, titles, stickers / GIF / memes, picture-in-picture) and the user's genuine assets. Break down the voiceover, background music, sound effects (which visual event each one hits), and editing rhythm, then provide an executable remake plan (with capsule-cinema integration). Use this when the user provides a reference video and asks "How was this video made? / Is it AI? / What assets were used? / How can I remake it?"
Analyze a screen recording of a manual process and produce targeted, working automation scripts. Extracts frames and audio narration from video files, reconstructs the step-by-step workflow, and proposes automation at multiple complexity levels using tools already installed on the user machine.
Turn a screen recording of a UI (page load, navigation, redirect/auth flow, app startup) into an interactive paint timeline page. You get a full-window video, a timeline of each visual paint with timestamps and durations, and on-video flashes of what was painted (pink) versus what only moved (blue). Use when the user shares a screen recording (.mp4/.mov) and asks for a timeline of paints, frames, or visual changes, a filmstrip, load-performance breakdown, "what painted when", or how long each screen was shown.